All Issue

2024 Vol.44, Issue 5

Research Article

Development of a Power Generation Forecast Model that Reflects the Degradation Conditions of Solar Modules: For AI Technique Approach

태양광 모듈의 열화 조건을 반영한 발전량 예측 모델 개발: AI 기법 접근을 위하여

Su-Wung Baek1
,
Sung-Gi Kwon2
,
Chang-heon Kim3*
,
Gye-Choon Park4
백 수웅1
,
권 성기2
,
김 창헌3*
,
박 계춘4
1PhD Student, Department of Electrical Engineering, Mokpo National University/Director, Enterprise Support Division, Energy Valley Enterprise Development Institute
2Instructor, Department of Electrical Engineering, Mokpo National University
3Senior Researcher, Artificial Intelligence & Energy Research Center, Korea Photonics Technology Institute
4Professor, Department of Electrical Engineering, Mokpo National University
1목포대학교 전기공학과, 박사과정/에너지밸리기업개발원 기업지원실, 실장
2목포대학교 전기공학과, 강사
3한국광기술원 AI에너지연구센터, 선임연구원
4목포대학교 전기공학과, 교수
*Corresponding Author
30 October 2024. pp. 1-10
PDF XML Citation
Abstract

This study highlights the significance of solar power as a renewable energy source and addresses the challenge of solar module degradation, which comprises the accuracy of power-generation forecasts. Traditional forecasting methods depend on facility capacity and average solar irradiance data; however, these methods are prone to intermittency and high uncertainty. In contrast, this study analyzed the degradation of solar modules and proposed an AI-based forecasting model that incorporates these degradation conditions. Indoor and outdoor tests were conducted to measure the I–V characteristics and assess module degradation conditions under various environmental stresses, resulting in the development of a comprehensive database. The study revealed that calculating the annual degradation rate significantly improved forecast accuracy, reducing the average error rate to 0.82%, thereby achieving the research objectives. This research is noteworthy as it enhances forecasting accuracy by introducing a model that accounts for the degradation of solar modules.

Keywords
Power generation forecast
Solar module degradation
Degradation forecasting algorithms
Photovoltaic system
키워드
발전량 예측
태양광 모듈 열화
열화 예측 알고리즘
태양광 발전
References
1

Korea Energy Agency, Statistical Analysis Division, Results of the Finalized Statistics on New and Renewable Energy Supply in 2022 (Announced in 2023), National Statistical Approval (Consultation) No. 337001, Ulsan, Republic of Korea, 2023.

2

Korea Energy Agency, New&Renewable Energy Center, Renewable Energy White Paper, 11-1410000-001321-11, Ulsan, Republic of Korea, 2022.

3

Nam, W., An Analytial Model for Degradation Rate of High Density Power PV Module using Latent Heat Analysis of Concurrent Temperature and Humidity Cycles with Light Soaking, Doctoral thesis, Konkuk University, 2021.

4

Kwon, K.-S., Review of the Special Act on the Promotion of Distributed Energy (Proposal), Korean Local Government Law Association, Vol. 77, No. 23-1, pp. 139-180, 2023.

5

Kim, W.-S. and Jo, H.-H., Impact of Photovoltaic Generation Expansion on Korea's Electricity Power System and the Solutions: Focusing on Power System Stability and Supply-and-demand Stability, The Korean Journal of Economic, Vol. 27, No. 1, pp. 23-65, 2020.

10.46228/KJE.27.1.2
6

Naveed Akhter, M., Mekhilef, S., Mokhlis, H., and Mohamed Shah, N., Review on Forecasting of Photovoltaic Power Generation Based on Machine Learning and Metaheuristic Techniques, IET Renewable Power Generation, Vol. 13, No. 7, pp. 1009-1023, 2019.

10.1049/iet-rpg.2018.5649
7

Lee, J.-I., Park, W.-K., Lee, I.-W., and Kim, S.-H., Comparison of Solar Power Prediction Model Based on Statistical and Artificial Intelligence Model and Analysis of Revenue for Forecasting Policy, Journal of IKEEE, Vol. 26, No. 3, pp. 355-363, 2022.

8

Song, J.-J., Jeong, Y.-S., and Lee, S.-H., Analysis of Prediction Model for Solar Power Generation, Journal of Digital Convergence, Vol. 12, No. 3, pp. 243-248, 2014.

10.14400/JDC.2014.12.3.243
9

Kim, K.-D., The Development of the Short-Term Predict Model for Solar Power Generation, Journal of the Korean Solar Energy Society, Vol. 33, No. 6, pp. 62-69, 2013.

10.7836/kses.2013.33.6.062
10

Huang, H., Xu, J, Peng, Z., Yoo, S., Yu, D., Huang, D., and Qin, H., Cloud Motion Estimation for Short Term Solar Irradiation Prediction, SmartGrid Communications IEEE International Conference, pp. 696-701, 21 October 2013, Vancouver, BC, Canada.

10.1109/SmartGridComm.2013.6688040
11

Na, H. and Kim, K., Study on Generation Volume of Floating Solar Power Using Historical Insolation Data, KSCE Journal of Civil and Environment Engineering Research, Vol. 43, No. 2, pp. 249-258, 2023.

12

Mohammad, A. and Mahjabeen F., Revolutionizing Solar Energy: The Impact of Artificial Inteligence on Photovoltaic Systems, International Journal of Multidisciplinary Scurnces and Arts, Vol. 2, No. 1, pp. 117-127, 2023.

10.47709/ijmdsa.v2i1.2599
13

Cabtillo-Luna, S., Moreno-Chuquen, R., Celeita D., and Anders G., Deep and Machine Learning Models to Forecast Photovoltaic Power Generation, Energies, Vol. 16, No. 10, pp. 4097-4121, 2023.

10.3390/en16104097
14

Korea Industrial Standards Council, Photovoltaic Devices-Procedures for Temperature and Irraduance Corrections to Measured I-V Characteristics, Eumseong, Republic of Korea, 2005.

Information
  • Publisher :Korean Solar Energy Society
  • Publisher(Ko) :한국태양에너지학회
  • Journal Title :Journal of the Korean Solar Energy Society
  • Journal Title(Ko) :한국태양에너지학회 논문집
  • Volume : 44
  • No :5
  • Pages :1-10
  • Received Date : 2024-08-01
  • Revised Date : 2024-08-30
  • Accepted Date : 2024-09-20
  • DOI :https://doi.org/10.7836/kses.2024.44.5.001
Journal Informaiton Journal of the Korean Solar Energy Society Journal of the Korean Solar Energy Society
Online Submission
  • NRF
  • KOFST
  • crossref crossmark
  • crossref cited-by
  • crosscheck
  • orcid
  • open access
  • ccl
Journal Informaiton Journal Informaiton - close